From Cognition to Context and Compute:
VecViz’s Path to its VNA Target Price and OpenBB App
The Founding Mission: Chart / Fundamental / Quant Synergy
Price is truth. Fundamentals reveal intrinsic value. Quant brings objectivity and scale. These three disciplines are often siloed on the buy side between the PM, Analyst, and Risk functions. Promoting the synergy between them was VecViz’s founding mission.
2021: The VSH Put Charts, Fundamental Narrative, Quant on the Same Page
The Vector Strength Histogram (VSH) was our initial core offering: one dashboard integrating all three disciplines, for the user to consider and draw conclusions from. At its core were major price chart tops and bottoms, from which channels were identified and scored1. Analyst-sourced narrative could be linked to the channels, and price probabilities that considered prospective price movement in terms of channel score traversed, could be overlaid.
But the VSH was out of step with the more cavalier and/or purely quant oriented investing styles that were becoming increasingly popular during 2021 (meme stocks, YOLO 0dte options, quant signals / robo-advisors, etc.). Furthermore, there was no source of narrative timelines available to us. We still believed in the mission, but we needed to pivot.
2023: The V-Score delivers VSH channel-based performance rankings
With the V-Score,3 VecViz attempted to grab investors’ attention rather than reward it. Instead of a display to study, it delivers a conclusion — a single directional signal. But the machine learning ensemble behind it considers only the VSH’s channel structure (chart), and resulting price probability distributions (quant). Narrative was not part of it, but how could it be? We had no source for narrative that scaled.
2025-2026: New Resources Clear the Path to Full Synergy Delivery
With Gemini’s 2.5 Pro, released in March 2025, VecViz suddenly had a source of fundamental narrative timelines possessing sufficient quality (in aggregate) that scaled.
Then, in summer 2025 we had our first intern cohort, followed by another in the winter. Several interns across those cohorts — Fathmat Samira Bakayoko, Sylvia Brennan, Bangrui Yan, and Daniel Coyne — helped us get over two key hurdles: 1) clarifying and streamlining our user interface for delivering narrative alongside charts and quant, and 2) calibrating what a ticker’s narrative implied in terms of price given the quant outlook for price volatility, broadly.
Also in summer 2025, with the help of Justin Lokos, we developed an app for OpenBB. Now our LLM sourced narrative was in the context of the OpenBB Copilot, alongside a myriad of related sources. An even higher level of synergy between charts, fundamentals, and quant was now possible.
By Spring 2026, we had developed the VNA Target Price, and deployed it in our app for the OpenBB Apps Marketplace. When scenario tested via our VNA What-If MCP tool, the chart / fundamental / quant synergy it delivers surpasses what we thought possible in 2021.
The VNA Target Price on OpenBB upgrades the VSH with Context and Compute
The VNA Target Price delivers what the VSH could only facilitate. The VSH lacked the comprehensive narrative coverage (the context), and the calibration of narrative to price such coverage allows (the compute), as explained in the algorithm below.
- Translate each LLM-sourced VecEvent’s2 bias and trend characterizations to expected channel width displacements from channel center4
- Sum those displacements across the Vector Sets they are tagged to, weighted by Vector Strength
- Compare the result to the displacement of actual ticker price from channel center
- Adjust that quantity to account for systematic differentials between LLM and market5
- Translate the adjusted quantity to the VNA Target Price by applying the average channel width in price terms
The VNA algorithm reflects the cognitive process the VSH was designed to inspire in the VSH user. The VNA user on VecViz’s app for OpenBB, in contrast, can engage with the VNA Target Price via the VNA What-If MCP tool we provide (also an aspect of the “compute”), allowing them to focus on which fundamental narratives to challenge and how.
With the algorithm transparent and the inputs clearly identified and displayed, the user can readily engage: by hand, by LLM prompt, or by MCP tool, whatever suits them best. And of course, the availability of additional content — earnings call transcripts, SEC filings, prediction markets, etc. on the OpenBB Workspace, alongside the VNA inputs, all in the context of the OpenBB Copilot — further upgrades engagement potential.
Higher Cognition of Value, Timing and Risk Through Context and Compute
The journey to chart/fundamental/quant synergy wasn’t as straight or short as we hoped, but we are thankful for it. First, of course, we are thankful for the relationships we made along the way. But we also acknowledge that without it we might not have the V-Score to help guide position timing, or the Vector Model price probability estimates6 that inform risk and option fair value considerations. Both are key complements to the VNA Target Price. Finally, our exploration of OpenBB’s Workspace encouraged us to develop the VNA, because we were excited about challenging it via the OpenBB Copilot.
As an app on OpenBB’s Apps Marketplace, VecViz’s views on valuation, timing, and risk can be in the same Copilot context as apps from other providers furnishing financial statements, earnings transcripts, analyst estimates, prediction markets, etc. Yet even higher cognition, attainable once again, via context and compute.
Get started with VecViz on OpenBB
Subscribe to the VecViz app to access the VNA Target Price, V-Score, Vector Strength Histogram, and all other VecViz analytics inside OpenBB Workspace.
1. Vector Strength is VecViz’s proprietary score for quantifying the support or resistance a Vector Set price channel is likely to exert. It is driven by three factors: price and date proximity, and top and bottom (including minor tops and bottoms) touch count. The Vector Strength Histogram displays a sampling of each channel considered together, with horizontal bars at their model date terminal point indicating their relative Vector Strength. See the VecViz FAQ & Definitions for a full definition of Vector Strength and Vector Sets.
2. VecEvents are the news themes and catalysts linked to the price tops and bottoms anchoring the Vector Set channels. See the VecViz FAQ & Definitions for a full definition and examples of VecEvents and their channel tagging.
3. V-Score performance can be reviewed in the Reports section of our website. See the VecViz FAQ & Definitions for more on the V-Score.
4. Expected channel width displacements are calibrated to correspond to a 6-12 month forward time horizon on a base case, i.e., “Expected Body”, volatility basis. This is an expectation, not a validated performance claim. See the Reports section of our website for performance of our Expected Body price probability analytics. See the VecViz FAQ & Definitions for more on the Expected Body metric and Vector Model probability outputs.
5. Via simple linear regression of the differential upon the actual displacement, across all tickers in our coverage.
6. Vector Model Price Probability uses machine learning calibrated on chart shape features and forward price movement scaled in terms of support and resistance traversed. To help users contextualize those probabilities, VecViz also displays standard normal distribution based probabilities (not a VecViz product) which we refer to as Sigma, as a benchmark alongside the Vector Model’s own estimates. Both are visually overlaid atop the Vector Strength Histogram and provided in a table as well. See the VecViz FAQ & Definitions for more on Vector Model Price Probability and the Sigma reference distribution.